Recurrent neural-network-based physical model for the chin and other plucked-string instruments

A new physical model with neural networks is presented. The structure of th e network is designed for the analysis of plucked-string instruments, and t his network is also used as the corresponding synthesis engine. The propose d approach also provides a general and automatic way of determining suitabl e synthesis parameters by using a supervised neural network training algori thm with recorded sounds of a specific played instrument as the training ve ctor. This is a general method and can be used for any plucked-string instr ument. A traditional Chinese plucked-string instrument, called the Chin, is used as the target instrument to demonstrate this new synthesis method.