English

FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

Computation and Language 2022-05-26 v1 Machine Learning Sound Audio and Speech Processing

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.

Keywords

Cite

@article{arxiv.2205.12446,
  title  = {FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech},
  author = {Alexis Conneau and Min Ma and Simran Khanuja and Yu Zhang and Vera Axelrod and Siddharth Dalmia and Jason Riesa and Clara Rivera and Ankur Bapna},
  journal= {arXiv preprint arXiv:2205.12446},
  year   = {2022}
}