An input-conditioned layer selector, trained with top-k gating, lets speech foundation models drop encoder layers per sample while outperforming random dropping and matching early exit on four audio benchmarks.
We will restrict the discus- sion to dynamic depth only as it encapsulates the early exit and layer dropping approaches
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Input Conditioned Layer Dropping in Speech Foundation Models
An input-conditioned layer selector, trained with top-k gating, lets speech foundation models drop encoder layers per sample while outperforming random dropping and matching early exit on four audio benchmarks.