{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/speechmatrix-a-large-scale-mined-corpus-of","title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","arxiv_id":null,"date":null,"proceeding":null,"authors":[],"abstract":null,"url_abs":"https://research.facebook.com/publications/speechmatrix/","url_pdf":"https://scontent-lhr8-2.xx.fbcdn.net/v/t39.8562-6/310002966_605149234737289_5204270723809834290_n.pdf?_nc_cat=102&ccb=1-7&_nc_sid=ad8a9d&_nc_ohc=FN2KnupyKI0AX90B5UO&_nc_ht=scontent-lhr8-2.xx&oh=00_AT9iFWHchGOnkzVTmwiYIDElIXSnwilSGhDwRQdFh99rlA&oe=63560915https://scontent-lhr8-2.xx.fbcdn.net/v/t39.8562-6/310002966_605149234737289_5204270723809834290_n.pdf?_nc_cat=102&ccb=1-7&_nc_sid=ad8a9d&_nc_ohc=FN2KnupyKI0AX90B5UO&_nc_ht=scontent-lhr8-2.xx&oh=00_AT9iFWHchGOnkzVTmwiYIDElIXSnwilSGhDwRQdFh99rlA&oe=63560915","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only"},"code_links":[{"paper_slug":"speechmatrix-a-large-scale-mined-corpus-of","repo_url":"https://github.com/facebookresearch/fairseq","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"speechmatrix","name":"SpeechMatrix","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}