Cafe2 min read
CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition
Feature distillation is usually expected to add to logit distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic speech recognition (ASR), and analyze why through their gradients.
By Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi, Mohammadreza Zolfaghari, Rishabh Jain, Louis Lu, Changdae Park, Amril NazirarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 15, 2026.
Comments
Sign in to join the discussion.