An approach to Beethoven's 10th Symphony
This is an incremental application of existing methods to a new dataset in music generation, with no clear broader impact beyond this specific domain.
The paper tackled the problem of generating Beethoven's unfinished Tenth Symphony by training an LSTM neural network on his existing symphonic data, resulting in outputs whose structure varied based on the training data used.
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.