data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup
This work addresses speech recognition challenges in data-scarce domains, offering incremental improvements over existing methods.
The paper tackles the problem of improving self-supervised learning for speech representation in domains with limited data by proposing data2vec-aqc, which achieves up to 20.9% relative WER improvement over the state-of-the-art data2vec on LibriSpeech without a language model.
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% and 20.9% relative WER improvement over the existing state-of-the-art data2vec system over the test-clean and test-other sets, respectively of LibriSpeech, without the use of any language model (LM). Our proposed model also achieves up to 17.8\% relative WER gains over the baseline data2vec when fine-tuned on a subset of the Switchboard dataset. Code: https://github.com/Speech-Lab-IITM/data2vec-aqc.