Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning

TL;DR

This paper presents an automatic method for selecting and parametrizing data augmentations in contrastive self-supervised speech learning, improving downstream task performance without extensive hyper-parameter tuning.

Contribution

It introduces a conditional independence-based approach for automatic augmentation selection tailored to specific downstream tasks in speech representation learning.

Findings

Outperforms baseline augmentation strategies

Automatically adapts augmentations to downstream tasks

Qualitative analysis confirms meaningful augmentation choices

Abstract

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.