MACHINE LEARNING WORK


Generative Raw Audio Adversarial Networks

Publication

Implemented over 150 GAN architectures for instrument & sound effect sample generation, for exhaustive granular controlled experimental comparison, representing the largest multivariate analysis of structural model variations in this domain to date. This included the structurally novel PrismGAN & SBIGAN models, which both quantifiably succeed at eliminating spectral artifacts in inference. Analysis was performed along 79 metrics, including several novel spectral comparison methods for audio inference evaluation.

GenerationImage1 GenerationImage2 GenerationImage3 GenerationImage4