Artificial Evolution of Expressive Performance of Music: An Imitative Multi-Agent Systems Approach
Artificial Evolution of Expressive Performance of Music: An Imitative Multi-Agent Systems Approach
复制标题
DOI：
10.1162/comj.2010.34.1.80
复制
发表时间：
2010-03
影响因子：
--
通讯作者：
E. Miranda;Alexis Kirke;Qijun Zhang
中科院分区：
文献类型：
--
作者：
E. Miranda;Alexis Kirke;Qijun Zhang
本章介绍了一种模仿多智能体系统方法，基于智能体的个体参数化音乐规则来生成富有表现力的音乐表演。我们开发了一个称为 IMAP（模仿多代理执行器）的系统。除了研究模仿多主体范式的这种应用的有用性之外，还希望研究这种方法中多样性和多样性控制的固有特征：对于创造性应用（例如音乐表演）来说，这是一个理想的特征。为了帮助控制多样性，根据之前的表达性能研究使用参数化规则。这些是使用先前开发的音乐分析算法在代理中实现的。当进行实验时，我们发现智能体通过音乐表演来表达他们的偏好，并且可以生成和控制多样性。
This chapter introduces an imitative multi-agent system approach to generate expressive performances of music, based on agents’ individual parameterized musical rules. We have developed a system called IMAP (imitative multi-agent performer). Aside from investigating the usefulness of such an application of the imitative multi-agent paradigm, there is also a desire to investigate the inherent feature of diversity and control of diversity in this methodology: a desirable feature for a creative application, such as musical performance. To aid this control of diversity, parameterized rules are utilized based on previous expressive performance research. These are implemented in the agents using previously developed musical analysis algorithms. When experiments are run, it is found that agents are expressing their preferences through their music performances and that diversity can be generated and controlled.