{"id":"https://openalex.org/W4392909850","doi":"https://doi.org/10.1109/icassp48485.2024.10446620","title":"M2BART: Multilingual and Multimodal Encoder-Decoder Pre-Training for Any-to-Any Machine Translation","display_name":"M2BART: Multilingual and Multimodal Encoder-Decoder Pre-Training for Any-to-Any Machine Translation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909850","doi":"https://doi.org/10.1109/icassp48485.2024.10446620"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446620","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":"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/A5072019513","display_name":"Peng\u2010Jen Chen","orcid":"https://orcid.org/0000-0001-5400-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng-Jen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672423","display_name":"Bowen Shi","orcid":"https://orcid.org/0000-0002-0689-9964"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102631567","display_name":"Kelvin Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kelvin Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ann Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47733963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"11896","last_page":"11900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9860000014305115,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9860000014305115,"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/machine-translation","display_name":"Machine translation","score":0.8668542504310608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7980372905731201},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6921327710151672},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5754454135894775},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5458486676216125},{"id":"https://openalex.org/keywords/machine-translation-system","display_name":"Machine translation system","score":0.545485258102417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5125179290771484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112431049346924},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4427459239959717},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0871671736240387}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8668542504310608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980372905731201},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6921327710151672},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5754454135894775},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5458486676216125},{"id":"https://openalex.org/C2986258472","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation system","level":3,"score":0.545485258102417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5125179290771484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112431049346924},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4427459239959717},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0871671736240387},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446620","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":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2799473636","https://openalex.org/W2962784628","https://openalex.org/W2979476256","https://openalex.org/W2995181338","https://openalex.org/W3015698636","https://openalex.org/W3030437843","https://openalex.org/W3034999214","https://openalex.org/W3095410713","https://openalex.org/W3101648800","https://openalex.org/W3119308075","https://openalex.org/W3140429000","https://openalex.org/W3173767661","https://openalex.org/W3180374548","https://openalex.org/W3196509775","https://openalex.org/W3198429080","https://openalex.org/W3203407300","https://openalex.org/W3205644108","https://openalex.org/W3207222250","https://openalex.org/W3209059054","https://openalex.org/W4221155340","https://openalex.org/W4223622550","https://openalex.org/W4226120743","https://openalex.org/W4226507725","https://openalex.org/W4285077564","https://openalex.org/W4287854499","https://openalex.org/W4296070387","https://openalex.org/W4307323391","https://openalex.org/W4372191700","https://openalex.org/W4385570550","https://openalex.org/W4385571229","https://openalex.org/W4385573012","https://openalex.org/W4392979802","https://openalex.org/W6769196770","https://openalex.org/W6769263558","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6788335241","https://openalex.org/W6790356757","https://openalex.org/W6803092890","https://openalex.org/W6810259195","https://openalex.org/W6841035593","https://openalex.org/W6846857581"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2890508380","https://openalex.org/W2985371315","https://openalex.org/W2917029047","https://openalex.org/W2061528982","https://openalex.org/W4391982595","https://openalex.org/W2962789428","https://openalex.org/W2963598809","https://openalex.org/W4388052519"],"abstract_inverted_index":{"Speech":[0],"and":[1,18,29,45,59,61,71,74,81],"language":[2],"models":[3,25],"are":[4],"advancing":[5],"towards":[6],"universality.":[7],"A":[8],"single":[9],"model":[10,94],"can":[11],"now":[12],"handle":[13],"translations":[14],"across":[15],"200":[16],"languages":[17,35],"transcriptions":[19],"for":[20,48,68],"over":[21],"100":[22],"languages.":[23],"Universal":[24],"simplify":[26],"development,":[27],"deployment,":[28],"importantly,":[30],"transfer":[31],"knowledge":[32],"to":[33],"less-resourced":[34],"or":[36],"modes.":[37],"This":[38],"paper":[39],"introduces":[40],"M2BART,":[41],"a":[42,53,65],"streamlined":[43],"multilingual":[44],"multimodal":[46],"framework":[47],"encoderdecoder":[49],"models.":[50],"It":[51],"employs":[52],"self-supervised":[54],"speech":[55,58],"tokenizer,":[56],"bridging":[57],"text,":[60],"is":[62],"pre-trained":[63],"with":[64],"unified":[66],"objective":[67],"both":[69],"unimodal":[70],"multimodal,":[72],"unsupervised":[73],"supervised":[75],"data.":[76,101],"When":[77],"tested":[78],"on":[79],"Spanish-to-English":[80],"English-to-Hokkien":[82],"translations,":[83],"M2BART":[84],"consistently":[85],"surpassed":[86],"competitors.":[87],"We":[88],"also":[89],"showcase":[90],"an":[91],"innovative":[92],"translation":[93],"enabling":[95],"zero-shot":[96],"transfers":[97],"even":[98],"without":[99],"labeled":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
