{"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/fleurs-few-shot-learning-evaluation-of","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","arxiv_id":"2205.12446","date":"2022-05-25","proceeding":null,"authors":["Alexis Conneau","Min Ma","Simran Khanuja","Yu Zhang","Vera Axelrod","Siddharth Dalmia","Jason Riesa","Clara Rivera","Ankur Bapna"],"abstract":"We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of the machine translation FLoRes-101 benchmark, with approximately 12 hours of speech supervision per language. FLEURS can be used for a variety of speech tasks, including Automatic Speech Recognition (ASR), Speech Language Identification (Speech LangID), Translation and Retrieval. In this paper, we provide baselines for the tasks based on multilingual pre-trained models like mSLAM. The goal of FLEURS is to enable speech technology in more languages and catalyze research in low-resource speech understanding.","url_abs":"https://arxiv.org/abs/2205.12446v1","url_pdf":"https://arxiv.org/pdf/2205.12446v1.pdf","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":"abstracts"},"code_links":[{"paper_slug":"fleurs-few-shot-learning-evaluation-of","repo_url":"https://github.com/samsunglabs/myqasr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"language-identification","task_name":"Language Identification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"speech-language-identification","task_name":"Speech Language Identification"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[{"slug":"fleurs","name":"FLEURS","full_name":"Few-shot Learning Evaluation of Universal Representations of Speech"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.12446","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}