@article{bestrq2contextualizethenpredictatwostepa,
  title = {BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations},
  author = {Ludovic K. Tuncay and Etienne Labbé and Thomas Pellegrini},
  year = {2026},
  eprint = {2606.30700},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.30700},
}