Reducing Domain mismatch in Self-supervised speech pre-training

Masked speech modeling (MSM) methods such as wav2vec2
or w2v-BERT learn representations over speech frames which
are randomly masked within an utterance. While these methods
improve performance of Automatic Speech Recognition (ASR)
systems, they have one major limitation. They treat all unsupervised
speech samples with equal weight, which hinders learning
as not all samples have relevant information to learn meaningful
representations. In this work, we address this limitation. We
propose ask2mask (ATM), a novel approach to focus on specific
samples during MSM pre-training. ATM employs an external
ASR model or scorer to weight unsupervised input samples by
performing a fine-grained data selection. ATM performs masking
over the highly confident input frames as chosen by the scorer.
This allows the model to learn meaningful representations. We
conduct fine-tuning experiments on two well-benchmarked corpora:
LibriSpeech (matching the pre-training data) and, AMI
and CHiME-6 (not matching the pre-training data). The results
substantiate the efficacy of ATM on significantly improving the
recognition performance under mismatched conditions while
still yielding modest improvements under matched conditions.