music-9

Music Modeling

3260 papers • 126 benchmarks • 313 datasets

( Image credit: R-Transformer )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in music-modeling-9

Trend

Dataset

Best Model

Actions

JSB Chorales

Nottingham

Libraries

i

Use these libraries to find music-modeling-9 models and implementations

ratschlab/HIRID-ICU-Benchmark

2 papers 48

Datasets

JSB Chorales

Music21

Lakh MIDI Dataset

Lakh Pianoroll Dataset

Nottingham

JS Fake Chorales

Subtasks

No subtasks available.

Most implemented papers

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

J. Z. Kolter, V. Koltun, Shaojie Bai•Sat Mar 03 2018

A systematic evaluation of generic convolutional and recurrent architectures for sequence modeling concludes that the common association between sequence modeling and recurrent networks should be reconsidered, and convolutionals should be regarded as a natural starting point for sequence modeled tasks.

6029

Content

rvandewater/yaib

2 papers 32

0

Paper Graph

LSTM: A Search Space Odyssey

J. Schmidhuber, Klaus Greff, R. Srivastava, Jan Koutník, Bas R. Steunebrink•Thu Mar 12 2015

This paper presents the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling, and observes that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.

5933 0

Paper Graph

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Yoshua Bengio, Junyoung Chung, Kyunghyun Cho, Çaglar Gülçehre•Tue Dec 09 2014

These advanced recurrent units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU), are found to be comparable to LSTM.

14186 0

Paper Graph

Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions

Yi-Hsuan Yang, Yu-Siang Huang•Fri Jan 31 2020

A Pop Music Transformer is built that composes Pop piano music with better rhythmic structure than existing Transformer models, when the way a musical score is converted into the data fed to a Transformer model is improved.

363 0

Paper Graph

Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset

S. Dieleman, Erich Elsen, Jesse Engel, Curtis Hawthorne, Andriy Stasyuk, Adam Roberts, Ian Simon, Cheng-Zhi Anna Huang, D. Eck•Sun Oct 28 2018

By using notes as an intermediate representation, a suite of models capable of transcribing, composing, and synthesizing audio waveforms with coherent musical structure on timescales spanning six orders of magnitude are trained, a process the authors call Wave2Midi2Wave.

532 0

Paper Graph

Counterpoint by Convolution

Aaron C. Courville, Adam Roberts, Cheng-Zhi Anna Huang, D. Eck, Tim Cooijmans•Sun Mar 17 2019

This model is an instance of orderless NADE, which allows more direct ancestral sampling, and finds that Gibbs sampling greatly improves sample quality, which is demonstrated to be due to some conditional distributions being poorly modeled.

159 0

Paper Graph

Gating Revisited: Deep Multi-Layer RNNs That can be Trained

K. Schindler, J. D. Wegner, Mehmet Ozgur Turkoglu, Stefano D'aronco•Tue Sep 24 2019

A new STAckable Recurrent cell (STAR) is proposed for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.

61 0

Paper Graph

Rethinking Neural Operations for Diverse Tasks

Christopher R'e, Ameet Talwalkar, M. Khodak, Nicholas Roberts, Tri Dao, Liam Li•Sun Mar 28 2021

This work introduces a search space of operations called XD-Operations that mimic the inductive bias of standard multi-channel convolutions while being much more expressive: it is proved that it includes many named operations across multiple application areas.

25 0

Paper Graph

Adding a benchmark result helps the community track progress.