@misc{whetten2026studydataselectionstrategies, title={A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models}, author={Ryan Whetten and Titouan Parcollet and Marco Dinarelli and Yannick Estève}, year={2026}, eprint={2601.20896}, archivePrefix={arXiv}, primaryClass={cs.SD}, url={https://arxiv.org/abs/2601.20896}, }