The Effects of Signal-to-Noise Ratio on Generative Adversarial Networks Applied to Marine Bioacoustic Data
It addresses the challenge of low SNR in marine bioacoustic data for researchers using GANs, but appears incremental as it focuses on evaluating effects rather than introducing new methods.
This paper investigated how signal-to-noise ratio (SNR) affects the performance of generative adversarial networks (GANs), specifically WaveGAN, on marine bioacoustic data, finding interesting results on SNR's impact through three evaluation methodologies.
In recent years generative adversarial networks (GANs) have been used to supplement datasets within the field of marine bioacoustics. This is driven by factors such as the cost to collect data, data sparsity and aid preprocessing. One notable challenge with marine bioacoustic data is the low signal-to-noise ratio (SNR) posing difficulty when applying deep learning techniques such as GANs. This work investigates the effect SNR has on the audio-based GAN performance and examines three different evaluation methodologies for GAN performance, yielding interesting results on the effects of SNR on GANs, specifically WaveGAN.