On Different Symbolic Music Representations for Algorithmic Composition Approaches Based on Neural Sequence Models

Abstract

Among the different approaches for automated music composition, those based on neural sequence models like the transformer show particular promise. A critical aspect for such approaches is how given music data sets are represented, or tokenised, for serving as suitable inputs for such models, as the choice of representation influences the quality of the produced output. In this paper, we introduce seven novel tokenisation techniques for converting MIDI data into numeric sequences. We compare characteristics of our tokenisers based on sets of musical data translated using our approaches. Our results show that some of our techniques greatly outperform the approaches found in the literature with respect to different metrics such as sequence length, information density, or memory requirements. Moreover, to evaluate the influence of our tokenisation approaches on the quality of the output of a model, we trained an ensemble of transformer models on the sets of tokenised musical data and performed a user study to assess the quality of the generated music pieces. The result of the study shows that the quality of pieces produced using our most promising techniques is equal to or outperforms state-of-the-art approaches.