Songs could be sampled multiple times to produce additional training samples, with some danger of overlap between samples. This resulted in our discriminator input matrix (and generator output matrix) being of size 384 x 128. Each slice contained a vector of size 128 to hold the volume of each possible note that could be played. In order to facilitate this, every musical training input was extracted as a 16 beat segment from a song, where each beat was divided into 24 time slices. In order to effectively utilize convolution within a GAN, the data used must maintain translational invariance. To make this task more feasible, we only used songs from the classical music genre with a single track and we fixed the amount of data that we used from each song. This introduces a significant amount of variability that must be captured, certainly too much to for a single 2D array. A single song can have multiple instruments playing their own part at any time. However, music is structured differently than images. 1 channel for greyscale or 3 channels for red-green-blue). With images, data representation is relatively straightforward images are just 2-dimensional arrays with a number of color channels (e.g. With this brief introduction to GANs out of the way, we’ll take a look at how we applied this concept to music. This feedback loop results in obtaining better and better generated content. The idea is that when one of these networks gets better at its job, the other network has to learn how to better counteract its adversary. The generator is challenged with creating authentic-looking content that fools the discriminator into believing it’s real. The discriminator has the task of determining whether or not input it is given is “real” or “fake”. GANs consist of two neural networks with conflicting goals, namely a discriminator and a generator. Given their positive results regarding image generation, we sought to find out if GANs could be applied to musical compositions with a similar outcome.įor some context, let’s briefly examine what a GAN actually is. Websites like showcase the capabilities of GANs in generating extraordinarily realistic human faces. Generative Adversarial Networks (GANs) have become extraordinarily popular in recent years due to their success with image generation.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
March 2023
Categories |