Chapter

Speech, Audio, Image and Biomedical Signal Processing using Neural Networks

Volume 83 of the series Studies in Computational Intelligence pp 191-215

Democratic Liquid State Machines for Music Recognition

  • Leo PapeAffiliated withDepartment of Physical Geography, Utrecht University
  • , Jornt de GruijlAffiliated withIntelligent Systems Group, Department of Information and Computing Sciences, Utrecht University
  • , Marco WieringAffiliated withIntelligent Systems Group, Department of Information and Computing Sciences, Utrecht University

* Final gross prices may vary according to local VAT.

Get Access

The liquid state machine (LSM) is a relatively new recurrent neural network (RNN) architecture for dealing with time-series classification problems. The LSMhas some attractive properties such as a fast training speed compared with more traditional RNNs, its biological plausibility, and its ability to deal with highly nonlinear dynamics. This paper presents the democratic LSM, an extension of the basic LSM that uses majority voting by combining two dimensions. First, instead of only giving the classification at the end of the time-series, multiple classifications after different time-periods are combined. Second, instead of using a single LSM, multiple ensembles are combined. The results show that the democratic LSM significantly outperforms the basic LSM and other methods on two music composer classification tasks where the goal is to separate Haydn/Mozart and Beethoven/Bach, and a music instrument classification problem where the goal is to distinguish between a flute and a bass guitar.