Using a Bi-directional LSTM Model with Attention Mechanism trained on MIDI Data for Generating Unique Music

TL;DR

This paper presents a bi-directional LSTM with attention mechanism trained on MIDI data to generate music that mimics the style of the training data, allowing for customizable parameters like tempo and instruments.

Contribution

It introduces a novel neural network model combining bi-directional LSTM and attention for music generation from MIDI data, enabling style mimicry and parameter customization.

Findings

Generated music follows the training style.

Model allows post-generation parameter adjustments.

Effective in capturing musical themes.

Abstract

Generating music is an interesting and challenging problem in the field of machine learning. Mimicking human creativity has been popular in recent years, especially in the field of computer vision and image processing. With the advent of GANs, it is possible to generate new similar images, based on trained data. But this cannot be done for music similarly, as music has an extra temporal dimension. So it is necessary to understand how music is represented in digital form. When building models that perform this generative task, the learning and generation part is done in some high-level representation such as MIDI (Musical Instrument Digital Interface) or scores. This paper proposes a bi-directional LSTM (Long short-term memory) model with attention mechanism capable of generating similar type of music based on MIDI data. The music generated by the model follows the theme/style of the music the model is trained on. Also, due to the nature of MIDI, the tempo, instrument, and other parameters can be defined, and changed, post generation.