Attentional networks for music generation
Audio and Speech Processing
2020-02-11 v1 Machine Learning
Sound
Machine Learning
Abstract
Realistic music generation has always remained as a challenging problem as it may lack structure or rationality. In this work, we propose a deep learning based music generation method in order to produce old style music particularly JAZZ with rehashed melodic structures utilizing a Bi-directional Long Short Term Memory (Bi-LSTM) Neural Network with Attention. Owing to the success in modelling long-term temporal dependencies in sequential data and its success in case of videos, Bi-LSTMs with attention serve as the natural choice and early utilization in music generation. We validate in our experiments that Bi-LSTMs with attention are able to preserve the richness and technical nuances of the music performed.
Cite
@article{arxiv.2002.03854,
title = {Attentional networks for music generation},
author = {Gullapalli Keerti and A N Vaishnavi and Prerana Mukherjee and A Sree Vidya and Gattineni Sai Sreenithya and Deeksha Nayab},
journal= {arXiv preprint arXiv:2002.03854},
year = {2020}
}