Symbolic Music Playing Techniques Generation as a Tagging Problem
This addresses a gap in symbolic music generation by focusing on playing techniques, which are important for realism, but the approach appears incremental as it adapts tagging methods to a specific domain.
The paper tackles the problem of generating playing techniques for symbolic music by framing it as a tagging problem, proposing a model that uses current data and external knowledge, and shows in experiments on Chinese bamboo flute music that it makes generated music more lively.
Music generation has always been a hot topic. When discussing symbolic music, melody or harmonies are usually seen as the only generating targets. But in fact, playing techniques are also quite an important part of the music. In this paper, we discuss the playing techniques generation problem by seeing it as a tagging problem. We propose a model that can use both the current data and external knowledge. Experiments were carried out by applying the proposed model in Chinese bamboo flute music, and results show that our method can make generated music more lively.