( Image credit: R-Transformer )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Through the paper, we show how Gaussian mixtures taking into account music metadata information can be used as an effective prior for the autoencoder latent space, introducing the first Music Adversarial Autoencoder (MusAE).
We show that training a neural network to predict a seemingly more complex sequence, with extra features included in the series being modeled, can improve overall model performance significantly.
SOTA for Music Modeling on JSB Chorales
We propose a new stackable recurrent cell (STAR) for recurrent neural networks (RNNs) that has significantly less parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.
#2 best model for Sequential Image Classification on Sequential MNIST (Unpermuted Accuracy metric)
Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales.
Based on this, we introduce a method for descriptor-based synthesis and show that we can control the descriptors of an instrument while keeping its timbre structure.
Our results indicate that a simple convolutional architecture outperforms canonical recurrent networks such as LSTMs across a diverse range of tasks and datasets, while demonstrating longer effective memory.
Our goal is to be able to build a generative model from a deep neural network architecture to try to create music that has both harmony and melody and is passable as music composed by humans.