AI RESEARCH

HARNESS: Lightweight Distilled Arabic Speech Foundation Models

arXiv CS.AI

ArXi:2604.14186v1 Announce Type: cross Large self-supervised speech (SSL) models achieve strong downstream performance, but their size limits deployment in resource-constrained settings. We present HArnESS, an Arabic-centric self-supervised speech model family trained from scratch with iterative self-distillation, together with lightweight student variants that offer strong accuracy-efficiency trade-offs on Automatic Speech Recognition (ASR), Dialect Identification (DID), and Speech Emotion Recognition.