Musical Instrument Classification using Democratic Liquid State Machines

The Liquid State Machine (LSM) is a relatively new recurrent neural network architecture, in which a static recurrent spiking neural network referred to as a ‘liquid’ and a trainable read-out network are combined to tackle time-series data. In this paper we describe the Democratic Liquid State Machine (DLSM) that uses an ensemble of single LSMs. We investigated the feasibility of the two LSM architectures as a complex spectrum analyzer over a broad frequency range using a musical instrument classification task in which bass guitar and flute had to be recognized by timbre. The experiments showed that single LSMs correctly classified 96% of all test samples, whereas the DLSMs classified 99% of all test samples correctly, improving overall performance to near perfection.