StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks

In this paper we introduce StyleWaveGAN, a style-based drum sound generator that is a variation of StyleGAN, a state-of-the-art image generator [1, 2]. By conditioning StyleWaveGAN on both the type of drum and several audio descriptors, we are able to synthesize waveforms faster than real-time on a GPU directly in CD quality up to a duration of 1.5s while retaining a considerable amount of control over the generation. We also introduce an alterna-tive to the progressive growing of GANs and experimented on the effect of dataset balancing for generative tasks. The experiments are carried out on an augmented subset of a publicly available dataset comprised of different drums and cymbals. We evaluate against two recent drum genera-tors, WaveGAN [3] and NeuroDrum [4], demonstrating significantly improved generation quality (measured with the Frechet Audio Distance) and interesting results with perceptual features.