arXiv:2603.06310v2 Announce Type: replace-cross Abstract: Speech foundation models struggle with low-resource Pacific Indigenous languages because of severe data scarcity. Furthermore, full fine-tuning risks catastrophic forgetting. To address this gap, we present an empirical study adapting models to real-world Pacific datasets. We investigate the impact of data volume, adaptation strategies, and representational drift on speech foundation models for various Pacific languages. Additionally, we analyze a continual learning framework for sequential language acquisition. Empirical results across
Source: arXiv cs.CL — read the full report at the original publisher.