Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning
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.
Code (1)
Tasks
Contrastive LearningData AugmentationRepresentation LearningSpeech Representation LearningSimilar Papers 제목 키워드 기반
Contrastive Embeddings for Neural Architectures
The performance of algorithms for neural architecture search strongly depends on the parametrization of the search space. We use contrastive learning to identify networks across different initializations based on their d…
Contrastive LearningNeural Architecture SearchTransfer LearningGraph Contrastive Learning Automated
Self-supervised learning on graph-structured data has drawn recent interest for learning generalizable, transferable and robust representations from unlabeled graphs. Among many, graph contrastive learning (GraphCL) has …
Contrastive LearningRepresentation LearningSelf-Supervised LearningMulti-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
Recent advances in unsupervised deep graph clustering have been significantly promoted by contrastive learning. Despite the strides, most graph contrastive learning models face challenges: 1) graph augmentation is used t…
ClusteringContrastive LearningDiversityGraph ClusteringGuidelines for Augmentation Selection in Contrastive Learning for Time Series Classification
Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is…
Activity RecognitionContrastive LearningPrognosisTime Series+2Time Series Contrastive Learning with Information-Aware Augmentations
Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key…
Contrastive LearningOpen-Ended Question AnsweringRepresentation LearningTime Series