An approach to Beethoven's 10th Symphony

TL;DR

This paper explores using LSTM neural networks to analyze Beethoven's symphonic data, aiming to generate a plausible version of his unfinished Tenth Symphony by identifying patterns in his compositional style.

Contribution

It introduces a neural network approach to model Beethoven's symphonic style and generate new compositions based on his existing works, providing insights into his compositional patterns.

Findings

Generated music reflects the training data's structure.

Output variations depend on different training datasets.

The model captures key stylistic features of Beethoven's symphonies.

Abstract

Ludwig van Beethoven composed his symphonies between 1799 and 1825, when he was writing his Tenth symphony. As we dispose of a great amount of data belonging to his work, the purpose of this paper is to investigate the possibility of extracting patterns on his compositional model from symbolic data and generate what would have been his last symphony, the Tenth. A neural network model has been built based on the Long Short-Therm Memory (LSTM) neural networks. After training the model, the generated music has been analysed by comparing the input data with the results, and establishing differences between the generated outputs based on the training data used to obtain them. The structure of the outputs strongly depends on the symphonies used to train the network.