Dynamics Modeling of Musical String by Linear Scattering Recurrent Network

Abstract

Music synthesis by physical modeling methods becomes a major research topic in the related area when FM synthesis and Wavetable synthesis cannot satisfy the demanding users. Combining the property of wave propagation and the associate discrete-time implementation. It is possible to generate realistic and dynamic musical tones. In this paper, we first start from the modeling of a musical string by proposing a class of neural networks called Linear Scattering Recurrent Network (LSRN) which employs the measurement of the response of plucked string as the learning data such that the model can be trained to be a counterpart of the string in the synthesis domain. The correspondent learning algorithm and computer simulations are given to demonstrate the encouraging modeling results.