@article{efficientlyidentifyinglowqualitylanguage,
  title = {Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset},
  author = {Farhan Samir and Emily P. Ahn and Shreya Prakash and Márton Soskuthy and Vered Shwartz and Jian Zhu},
  year = {2024},
  eprint = {2410.04292},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.04292v1},
}