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

by   Salah Zaiem, et al.

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.


page 1

page 2

page 3

page 4


Contrasting Contrastive Self-Supervised Representation Learning Models

In the past few years, we have witnessed remarkable breakthroughs in sel...

Data Augmenting Contrastive Learning of Speech Representations in the Time Domain

Contrastive Predictive Coding (CPC), based on predicting future segments...

Contrastive Representation Learning for Acoustic Parameter Estimation

A study is presented in which a contrastive learning approach is used to...

Conditional independence for pretext task selection in Self-supervised speech representation learning

Through solving pretext tasks, self-supervised learning (SSL) leverages ...

Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals

Health-related acoustic signals, such as cough and breathing sounds, are...

Center-wise Local Image Mixture For Contrastive Representation Learning

Recent advances in unsupervised representation learning have experienced...

Pretext Tasks selection for multitask self-supervised speech representation learning

Through solving pretext tasks, self-supervised learning leverages unlabe...

Please sign up or login with your details

Forgot password? Click here to reset