新闻 · arXiv cs.CL
Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR
Large-scale pretrained ASR models such as Whisper exhibit strong multilingual capabilities. However, fine-tuning on low-resource languages often causes catastrophic forgetting. Although continual learning mitigates this issue, existing methods struggle to regulate cross-task interference in multilingual settings, where dominant languages bias optimization. We propose Unified Gradient Projection (UGP), which constrains parameter updates using reference gradients from language-balanced replay in…
en
