Wav2Vec-Aug: Improved self-supervised training with limited data. (arXiv:2206.13654v1 [cs.CL])

Self-supervised learning (SSL) of speech representations has received much
attention over the last few years but most work has focused on languages and
domains with an abundance of unlabeled data. However, for many languages there
is a shortage even in the unlabeled data which limits the effectiveness of SSL.
In this work, we focus on the problem of applying SSL to domains with limited
available data by leveraging data augmentation for Wav2Vec 2.0 pretraining.
Further, we propose improvements to each …

arxiv data training