Hypernetworks build Implicit Neural Representations of Sounds
Abstract
Implicit Neural Representations (INRs) are nowadays used to represent multimedia signals across various real-life applications, including image super-resolution, image compression, or 3D rendering. Existing methods that leverage INRs are predominantly focused on visual data, as their application to other modalities, such as audio, is nontrivial due to the inductive biases present in architectural attributes of image-based INR models. To address this limitation, we introduce HyperSound, the first meta-learning approach to produce INRs for audio samples that leverages hypernetworks to generalize beyond samples observed in training. Our approach reconstructs audio samples with quality comparable to other state-of-the-art models and provides a viable alternative to contemporary sound representations used in deep neural networks for audio processing, such as spectrograms.
Cite
@article{arxiv.2302.04959,
title = {Hypernetworks build Implicit Neural Representations of Sounds},
author = {Filip Szatkowski and Karol J. Piczak and Przemysław Spurek and Jacek Tabor and Tomasz Trzciński},
journal= {arXiv preprint arXiv:2302.04959},
year = {2023}
}
Comments
ECML2023