Automatic Data Augmentation Selection And Parametrization In Contrastive Self-supervised Speech Representation Learning

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 bett

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyzaiem2022automatic

Related papers

• Automatic Data Augmentation For Domain Adapted Fine-tuning Of Self-supervised Speech Representations (2023)0.00
• Augmentation Adversarial Training For Self-supervised Speaker Recognition (2020)0.00
• Self-supervised Learning From Contrastive Mixtures For Personalized Speech Enhancement (2020)0.00
• Pretext Tasks Selection For Multitask Self-supervised Speech Representation Learning (2021)8.60
• Speech Representation Learning Revisited: The Necessity Of Separate Learnable Parameters And Robust Data Augmentation (2024)0.00
• Reduce, Reuse, Recycle: Is Perturbed Data Better Than Other Language Augmentation For Low Resource Self-supervised Speech Models (2023)0.00
• Ccc-wav2vec 2.0: Clustering Aided Cross Contrastive Self-supervised Learning Of Speech Representations (2022)7.81
• Efficient Personalized Speech Enhancement Through Self-supervised Learning (2021)10.21