data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup
share
In this paper, we propose a new Self-Supervised Learning (SSL) algorithm called data2vec-aqc, for speech representation learning from unlabeled speech data. Our goal is to improve SSL for speech in domains where both unlabeled and labeled data are limited. Building on the recently introduced data2vec, we introduce additional modules to the data2vec framework that leverage the benefit of data augmentations, quantized representations, and clustering. The interaction between these modules helps solve the cross-contrastive loss as an additional self-supervised objective. data2vec-aqc achieves up to 14.1 20.9 system on the test-clean and test-other sets, respectively, of LibriSpeech, without the use of any language model. Our proposed model also achieves up to 17.8 Switchboard data.
READ FULL TEXT