Music Modeling
24 papers with code • 2 benchmarks • 6 datasets
( Image credit: R-Transformer )
Benchmarks
These leaderboards are used to track progress in Music Modeling
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Music Modeling models and implementations
Lakh MIDI Dataset
Music21
JSB Chorales
Nottingham
JS Fake Chorales
Most implemented papers
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
locuslab/TCN
•
•
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.
LSTM: A Search Space Odyssey
Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995.
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
In this paper we compare different types of recurrent units in recurrent neural networks (RNNs).
Music Transformer
This is impractical for long sequences such as musical compositions since their memory complexity for intermediate relative information is quadratic in the sequence length.
Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions
YatingMusic/remi
•
•
In contrast with this general approach, this paper shows that Transformers can do even better for music modeling, when we improve the way a musical score is converted into the data fed to a Transformer model.
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
BShakhovsky/PolyphonicPianoTranscription
•
•
ICLR 2019
Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales.
Counterpoint by Convolution
czhuang/coconet
•
•
Machine learning models of music typically break up the task of composition into a chronological process, composing a piece of music in a single pass from beginning to end.
Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.
Rethinking Neural Operations for Diverse Tasks
mkhodak/relax
•
•
NeurIPS 2021
An important goal of AutoML is to automate-away the design of neural networks on new tasks in under-explored domains.
Deep Learning for Music
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.
