PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations. (arXiv:2203.16965v2 [cs.CL] UPDATED)

While self-supervised speech representation learning (SSL) models serve a
variety of downstream tasks, these models have been observed to overfit to the
domain from which the unlabelled data originates. To alleviate this issue, we
propose PADA (Pruning Assisted Domain Adaptation) and zero out redundant
weights from models pre-trained on large amounts of out-of-domain (OOD) data.
Intuitively, this helps to make space for the target-domain ASR finetuning. The
redundant weights can be identified through various pruning strategies which
have been discussed …

arxiv domain adaptation pruning speech