Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning
This work addresses the challenge of optimizing data augmentations for researchers and practitioners in speech representation learning, offering an incremental improvement by automating selection and parameterization to enhance downstream task performance.
The paper tackles the problem of selecting and parameterizing data augmentations in contrastive self-supervised speech representation learning by introducing a conditional independence-based method that automates this process with respect to a downstream task, saving costly hyperparameter search. Experiments on two downstream tasks show better results than using no augmentations or baseline augmentations.
Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation techniques are usually exploited to help enforce desired invariances within the learned representations, improving performance on various audio tasks thanks to more robust embeddings. Now, selecting the most relevant augmentations has proven crucial for better downstream performances. Thus, this work introduces a conditional independance-based method which allows for automatically selecting a suitable distribution on the choice of augmentations and their parametrization from a set of predefined ones, for contrastive self-supervised pre-training. This is performed with respect to a downstream task of interest, hence saving a costly hyper-parameter search. Experiments performed on two different downstream tasks validate the proposed approach showing better results than experimenting without augmentation or with baseline augmentations. We furthermore conduct a qualitative analysis of the automatically selected augmentations and their variation according to the considered final downstream dataset.