Symbolic Music Playing Techniques Generation as a Tagging Problem

TL;DR

This paper introduces a novel approach to generate symbolic music playing techniques by framing it as a tagging problem, incorporating external knowledge to enhance the liveliness of the generated Chinese bamboo flute music.

Contribution

The paper presents a new model that treats playing techniques generation as a tagging task, integrating data and external knowledge for improved music synthesis.

Findings

Generated music is more lively and expressive.

The model effectively incorporates external knowledge.

Application to Chinese bamboo flute music demonstrates its practicality.

Abstract

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.