{"id":"https://openalex.org/W4384648564","doi":"https://doi.org/10.48550/arxiv.2307.08655","title":"Multilingual Speech-to-Speech Translation into Multiple Target Languages","display_name":"Multilingual Speech-to-Speech Translation into Multiple Target Languages","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4384648564","doi":"https://doi.org/10.48550/arxiv.2307.08655"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.08655","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.08655","pdf_url":"https://arxiv.org/pdf/2307.08655","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.08655","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gong, Hongyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gong, Hongyu","raw_affiliation_strings":["Meta AI Research , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research , USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong, Ning","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong, Ning","raw_affiliation_strings":["Meta AI Research , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research , USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059951425","display_name":"Sravya Popuri","orcid":"https://orcid.org/0009-0005-8585-1369","observed_orcids":["https://orcid.org/0009-0005-8585-1369"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Popuri, Sravya","raw_affiliation_strings":["Meta AI Research , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research , USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035752789","display_name":"Vedanuj Goswami","orcid":"https://orcid.org/0009-0005-5027-1452","observed_orcids":["https://orcid.org/0009-0005-5027-1452"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goswami, Vedanuj","raw_affiliation_strings":["Meta AI Research , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research , USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032","observed_orcids":["https://orcid.org/0000-0003-4300-9032"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee, Ann","raw_affiliation_strings":["Meta AI Research , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research , USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":"https://orcid.org/0009-0002-4895-7736","observed_orcids":["https://orcid.org/0009-0002-4895-7736"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pino, Juan","raw_affiliation_strings":["Meta AI Research , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research , USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.00039999998989515007,"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/T10181","display_name":"Natural Language Processing Techniques","score":9.999999747378752e-05,"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/speech-to-speech-translation","display_name":"speech-to-speech translation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/multilingual-translation","display_name":"multilingual translation","score":0.8610000014305115},{"id":"https://openalex.org/keywords/language-embedding","display_name":"language embedding","score":0.8769999742507935},{"id":"https://openalex.org/keywords/language-identification","display_name":"language identification","score":0.859000027179718},{"id":"https://openalex.org/keywords/language-transfer","display_name":"language transfer","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402156829833984},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6408582329750061},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5984212756156921},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5477281808853149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4973025619983673},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4756949841976166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43921875953674316},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41592320799827576},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3795771598815918},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3515036702156067},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.08655","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.08655","pdf_url":"https://arxiv.org/pdf/2307.08655","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.08655","doi":"https://doi.org/10.48550/arxiv.2307.08655","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.08655","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.08655","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.08655","pdf_url":"https://arxiv.org/pdf/2307.08655","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384648564.pdf","grobid_xml":"https://content.openalex.org/works/W4384648564.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2883671469"],"abstract_inverted_index":{"Speech-to-speech":[0],"translation":[1,30,115,129],"(S2ST)":[2],"enables":[3],"spoken":[4],"communication":[5],"between":[6],"people":[7],"talking":[8],"in":[9,54,127],"different":[10],"languages.":[11,50,135],"Despite":[12],"a":[13],"few":[14],"studies":[15],"on":[16,24,44],"multilingual":[17,45,67,73,98,119],"S2ST,":[18],"their":[19],"focus":[20],"is":[21,71,101],"the":[22,25,29,41,72,86,92,107,128],"multilinguality":[23],"source":[26,33],"side,":[27],"i.e.,":[28],"from":[31,130],"multiple":[32,48],"languages":[34],"to":[35,80,85,90],"one":[36],"target":[37,49,88,134],"language.":[38],"We":[39,95],"present":[40],"first":[42],"work":[43],"S2ST":[46,56],"supporting":[47],"Leveraging":[51],"recent":[52],"advance":[53],"direct":[55],"with":[57,66,103],"speech-to-unit":[58],"and":[59,106],"vocoder,":[60],"we":[61],"equip":[62],"these":[63],"key":[64],"components":[65],"capability.":[68],"Speech-to-masked-unit":[69],"(S2MU)":[70],"extension":[74],"of":[75,110],"S2U,":[76],"which":[77,82,100],"applies":[78],"masking":[79],"units":[81],"don't":[83],"belong":[84],"given":[87],"language":[89,93,104,111],"reduce":[91],"interference.":[94],"also":[96],"propose":[97],"vocoder":[99],"trained":[102],"embedding":[105],"auxiliary":[108],"loss":[109],"identification.":[112],"On":[113],"benchmark":[114],"testsets,":[116],"our":[117],"proposed":[118],"model":[120],"shows":[121],"superior":[122],"performance":[123],"than":[124],"bilingual":[125],"models":[126],"English":[131],"into":[132],"$16$":[133]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}