@misc{arxiv_2610_13102v1,
  title = {From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale},
  author = {{Yaroslav Getman} and {Tamás Grósz} and {Tommi Lehtonen} and {Mikko Kurimo}},
  eprint = {2610.13102v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.13102v1}
}