N. Kotecha, and P. Young. (2018)cite arxiv:1804.07300Comment: 8 pages, 11 figures.
Abstract
A model of music needs to have the ability to recall past details and have a
clear, coherent understanding of musical structure. Detailed in the paper is a
neural network architecture that predicts and generates polyphonic music
aligned with musical rules. The probabilistic model presented is a Bi-axial
LSTM trained with a kernel reminiscent of a convolutional kernel. When analyzed
quantitatively and qualitatively, this approach performs well in composing
polyphonic music. Link to the code is provided.
Description
[1804.07300] Generating Music using an LSTM Network
%0 Generic
%1 kotecha2018generating
%A Kotecha, Nikhil
%A Young, Paul
%D 2018
%K generation lstm music
%T Generating Music using an LSTM Network
%U http://arxiv.org/abs/1804.07300
%X A model of music needs to have the ability to recall past details and have a
clear, coherent understanding of musical structure. Detailed in the paper is a
neural network architecture that predicts and generates polyphonic music
aligned with musical rules. The probabilistic model presented is a Bi-axial
LSTM trained with a kernel reminiscent of a convolutional kernel. When analyzed
quantitatively and qualitatively, this approach performs well in composing
polyphonic music. Link to the code is provided.
@misc{kotecha2018generating,
abstract = {A model of music needs to have the ability to recall past details and have a
clear, coherent understanding of musical structure. Detailed in the paper is a
neural network architecture that predicts and generates polyphonic music
aligned with musical rules. The probabilistic model presented is a Bi-axial
LSTM trained with a kernel reminiscent of a convolutional kernel. When analyzed
quantitatively and qualitatively, this approach performs well in composing
polyphonic music. Link to the code is provided.},
added-at = {2018-04-23T12:41:29.000+0200},
author = {Kotecha, Nikhil and Young, Paul},
biburl = {https://www.bibsonomy.org/bibtex/2bbe492585a02b20324365d31620911ac/rcb},
description = {[1804.07300] Generating Music using an LSTM Network},
interhash = {5f480b74ae20ad817a09637c49ebe278},
intrahash = {bbe492585a02b20324365d31620911ac},
keywords = {generation lstm music},
note = {cite arxiv:1804.07300Comment: 8 pages, 11 figures},
timestamp = {2018-04-23T12:41:29.000+0200},
title = {Generating Music using an LSTM Network},
url = {http://arxiv.org/abs/1804.07300},
year = 2018
}