Modelling Symbolic Music: Beyond the Piano Roll
This work addresses the problem of generating more sophisticated symbolic music for researchers and musicians, though it is incremental as it builds on existing NLP techniques.
The paper tackles probabilistic modeling of symbolic music by introducing a representation that converts polyphonic music into a univariate categorical sequence, enabling the use of LSTM models, and shows effectiveness on four benchmark datasets with state-of-the-art results through data augmentation.
In this paper, we consider the problem of probabilistically modelling symbolic music data. We introduce a representation which reduces polyphonic music to a univariate categorical sequence. In this way, we are able to apply state of the art natural language processing techniques, namely the long short-term memory sequence model. The representation we employ permits arbitrary rhythmic structure, which we assume to be given. We show that our model is effective on four out of four piano roll based benchmark datasets. We further improve our model by augmenting our training data set with transpositions of the original pieces through all musical keys, thereby convincingly advancing the state of the art on these benchmark problems. We also fit models to music which is unconstrained in its rhythmic structure, discuss the properties of this model, and provide musical samples which are more sophisticated than previously possible with this class of recurrent neural network sequence models. We also provide our newly preprocessed data set of non piano-roll music data.