Music Modeling

22 papers with code • 2 benchmarks • 6 datasets

( Image credit: R-Transformer )

Libraries

Use these libraries to find Music Modeling models and implementations

Most implemented papers

R-Transformer: Recurrent Neural Network Enhanced Transformer

DSE-MSU/R-transformer ICLR 2020

Recurrent Neural Networks have long been the dominating choice for sequence modeling.

Improving Polyphonic Music Models with Feature-Rich Encoding

omarperacha/TonicNet 26 Nov 2019

We show that training a neural network to predict a seemingly more complex sequence, with extra features included in the series being modelled, can improve overall model performance significantly.

Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders

Andrea-V/MusAE 15 Jan 2020

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).

Sequential Neural Models with Stochastic Layers

marcofraccaro/srnn NeurIPS 2016

How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks?

Diagonal RNNs in Symbolic Music Modeling

ycemsubakan/diagonal_rnns 18 Apr 2017

In this paper, we propose a new Recurrent Neural Network (RNN) architecture.

Bivariate Beta-LSTM

gtshs2/BetaLSTM 25 May 2019

Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0, 1] through a sigmoid function.

Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling

f90/Seq-U-Net 14 Nov 2019

In comparison to TCN and Wavenet, our network consistently saves memory and computation time, with speed-ups for training and inference of over 4x in the audio generation experiment in particular, while achieving a comparable performance in all tasks.

PopMAG: Pop Music Accompaniment Generation

Natooz/MidiTok 18 Aug 2020

To improve harmony, in this paper, we propose a novel MUlti-track MIDI representation (MuMIDI), which enables simultaneous multi-track generation in a single sequence and explicitly models the dependency of the notes from different tracks.

Gates Are Not What You Need in RNNs

LUMII-Syslab/RRU 1 Aug 2021

In this paper, we propose a new recurrent cell called Residual Recurrent Unit (RRU) which beats traditional cells and does not employ a single gate.

Low-Rank Constraints for Fast Inference in Structured Models

justinchiu/low-rank-models NeurIPS 2021

This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models.