{"id":"https://openalex.org/W4385572318","doi":"https://doi.org/10.18653/v1/2023.acl-long.899","title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","display_name":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385572318","doi":"https://doi.org/10.18653/v1/2023.acl-long.899"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.899","pdf_url":"https://aclanthology.org/2023.acl-long.899.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-long.899.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059582849","display_name":"Paul-Ambroise Duquenne","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paul-Ambroise Duquenne","raw_affiliation_strings":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]},{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103000746","display_name":"Hongyu Gong","orcid":"https://orcid.org/0000-0002-7071-0070"},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hongyu Gong","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722683","display_name":"Ning Dong","orcid":"https://orcid.org/0000-0003-4089-8436"},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ning Dong","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006191011","display_name":"Jingfei Du","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jingfei Du","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ann Lee","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035752789","display_name":"Vedanuj Goswami","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vedanuj Goswami","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Changhan Wang","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077663332","display_name":"Beno\u00eet Sagot","orcid":"https://orcid.org/0000-0002-0107-8526"},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Beno\u00eet Sagot","raw_affiliation_strings":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)"],"affiliations":[{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","orcid":null},"institutions":[],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Holger Schwenk","raw_affiliation_strings":["Meta AI Research [Paris] (France)"],"affiliations":[{"raw_affiliation_string":"Meta AI Research [Paris] (France)","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.58,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":13,"citation_normalized_percentile":{"value":0.999976,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"16251","last_page":"16269"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9908,"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":0.9908,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9842,"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/T10028","display_name":"Topic Modeling","score":0.9546,"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/computational-linguistics","display_name":"Computational linguistics","score":0.52072906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57950497},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.536278},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.52072906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.47349438},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.45748842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45138934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44854352},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42691952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38301414},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2522374},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13621786},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11322805},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06665903},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04827845},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.899","pdf_url":"https://aclanthology.org/2023.acl-long.899.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04264040","pdf_url":"https://inria.hal.science/hal-04264040/document","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2211.04508","pdf_url":"https://arxiv.org/pdf/2211.04508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.899","pdf_url":"https://aclanthology.org/2023.acl-long.899.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Quality education","score":0.83,"id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W435830328","https://openalex.org/W4242592912","https://openalex.org/W4237443457","https://openalex.org/W2798121181","https://openalex.org/W2587527225","https://openalex.org/W2328676785","https://openalex.org/W2322380964","https://openalex.org/W2087896742","https://openalex.org/W2016805743","https://openalex.org/W1989025965"],"abstract_inverted_index":{"Paul-Ambroise":[0],"Duquenne,":[1],"Hongyu":[2],"Gong,":[3],"Ning":[4],"Dong,":[5],"Jingfei":[6],"Du,":[7],"Ann":[8],"Lee,":[9],"Vedanuj":[10],"Goswami,":[11],"Changhan":[12],"Wang,":[13],"Juan":[14],"Pino,":[15],"Beno\u00eet":[16],"Sagot,":[17],"Holger":[18],"Schwenk.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"61st":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2023.":[36]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4385572318","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7}],"updated_date":"2024-12-13T19:02:58.742365","created_date":"2023-08-05"}