Ask2Mask: Guided Data Selection for Masked Speech Modeling

Understand

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.