Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads

arXiv:2308.14456v2 Announce Type: replace-cross
Abstract: Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high number of proposed approaches fostered the emergence of comprehensive benchmarks that evaluate their performance on a set of downstream tasks exploring various aspects of the speech signal. However, while the number of considered tasks has been growing, most proposals rely upon a single downstream architecture that maps the frozen SSL representations to the task …

abstract annotated data arxiv benchmarking benchmarks case cs.lg cs.sd data datasets eess.as eess.sp emergence large datasets performance self-supervised learning set speech ssl supervised learning tasks type