Music Generation using Three-layered LSTM

TL;DR

This paper presents a method using three-layered LSTM neural networks to generate musical sequences in ABC notation, aiming to produce musically coherent pieces through sequence augmentation and parameter calibration.

Contribution

It introduces a novel application of three-layered LSTM networks for music generation in ABC notation, including data encoding and parameter tuning for improved output quality.

Findings

The LSTM model can generate musically coherent sequences.

Parameter calibration improves rhythm and harmony accuracy.

The approach demonstrates effective sequence augmentation.

Abstract

This paper explores the idea of utilising Long Short-Term Memory neural networks (LSTMNN) for the generation of musical sequences in ABC notation. The proposed approach takes ABC notations from the Nottingham dataset and encodes it to be fed as input for the neural networks. The primary objective is to input the neural networks with an arbitrary note, let the network process and augment a sequence based on the note until a good piece of music is produced. Multiple calibrations have been done to amend the parameters of the network for optimal generation. The output is assessed on the basis of rhythm, harmony, and grammar accuracy.