Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning

arXiv:2405.08679v1 Announce Type: cross
Abstract: This paper addresses the problem of self-supervised general-purpose audio representation learning. We explore the use of Joint-Embedding Predictive Architectures (JEPA) for this task, which consists of splitting an input mel-spectrogram into two parts (context and target), computing neural representations for each, and training the neural network to predict the target representations from the context representations. We investigate several design choices within this framework and study their influence through extensive experiments by evaluating our models on …

abstract architectures arxiv audio computing context cs.ai cs.lg cs.sd design eess.as embedding explore general jepa paper predictive representation representation learning spectrogram training type