Siamese SIREN: Audio Compression with Implicit Neural Representations
This work addresses audio compression for multimedia applications, but it is a preliminary investigation and incremental in scope.
The paper tackled audio compression using Implicit Neural Representations (INRs), introducing Siamese SIREN, which achieved better audio reconstruction fidelity with fewer network parameters than prior INR methods.
Implicit Neural Representations (INRs) have emerged as a promising method for representing diverse data modalities, including 3D shapes, images, and audio. While recent research has demonstrated successful applications of INRs in image and 3D shape compression, their potential for audio compression remains largely unexplored. Motivated by this, we present a preliminary investigation into the use of INRs for audio compression. Our study introduces Siamese SIREN, a novel approach based on the popular SIREN architecture. Our experimental results indicate that Siamese SIREN achieves superior audio reconstruction fidelity while utilizing fewer network parameters compared to previous INR architectures.