Classical Music Composition Using State Space Models
This work addresses music generation for AI and creative arts, but it is incremental as it applies existing models to a specific domain.
The authors tackled algorithmic composition of classical piano music using state space models like HMMs, finding that these models generate pieces with consonant harmonies but fail to produce realistic melodic progression.
Algorithmic composition of music has a long history and with the development of powerful deep learning methods, there has recently been increased interest in exploring algorithms and models to create art. We explore the utility of state space models, in particular hidden Markov models (HMMs) and variants, in composing classical piano pieces from the Romantic era and consider the models' ability to generate new pieces that sound like they were composed by a human. We find that the models we explored are fairly successful at generating new pieces that have largely consonant harmonies, especially when trained on original pieces with simple harmonic structure. However, we conclude that the major limitation in using these models to generate music that sounds like it was composed by a human is the lack of melodic progression in the composed pieces. We also examine the performance of the models in the context of music theory.