Quantized Generative Autoencoder for Audio Spectrograms

This study analyzes techniques for compressing generative autoencoders to enable their deployment on resource-constrained devices, addressing the challenges and optimizations required for such environments. As a case study, we present a quantized generative autoencoder optimized for efficiently generating underwater sound spectrograms. The model is evaluated across diverse scenarios, demonstrating its ability to produce low-dimensional spectrograms while adapting to various acoustic conditions. The hardware optimization process focuses on balancing computational efficiency and model accuracy, ensuring performance comparable to its non-quantized counterpart.