Neuro-inspired speech recognition based on reservoir computing

This chapter investigates the potential of recurrent spiking neurons for classification
problems. It presents a hybrid approach based on the paradigm of Reservoir Computing. The
practical applications based on recurrent spiking neurons are limited due to the lack of
learning algorithms. Most of the previous work in the literature has focused on feed forward
networks because computation in these networks is comparatively easy to analyse. The
details of such networks have been reported in detail in (Haykin, 1999) (Pavlidis et al., 2005)
(Bohte et al., 2000). Recently, a strategy proposed by Maass (Maass et al., 2002) and Jaeger
(Jaeger, 2001) offers to overcome the burden of recurrent neural networks training. In this
paradigm, instead of training the whole recurrent network only the output layer (known as
readout neuron) is trained.
This chapter investigates the potential of recurrent spiking neurons as the basic building
blocks for the liquid or so called reservoir. These recurrent neural networks are termed as
microcircuits which are viewed as basic computational units in cortical computation (Maass
et al., 2002). These microcircuits are connected as columns which are linked with other
neighboring columns in cortical areas. These columns read out information from each other
and serve both as reservoir and readout. The reservoir is modeled as a dynamical system
perturbed by the input stream where only readouts are trained to extract information from
the reservoir. The basic motivation behind investigating recurrent neurons is their potential
to memorise relevant events over short periods of time (Maass et al., 2002). The use of
feedback enables recurrent networks to acquire state representation which makes them
suitable for temporal based applications such as speech recognition. It is challenging to
solve such problems with recurrent networks due to the burden of training. The paradigm
of reservoir computing also referred to as liquid computing relaxes the burden of training
because only an output layer is trained instead of training the whole network. The work
presented in this chapter analyses the theoretical framework of Reservoir Computing and
demonstrates results in terms of classification accuracy through the application of speech
recognition. The design space for this paradigm is split into three domains; front end,
reservoir, and back end. This work contributes to the identification of suitable front and
back end processing techniques along with stable reservoir dynamics, which provides a
reliable framework for classification related problems.
The work presented in this chapter suggests a simple and efficient biologically plausible
approach based on a hybrid implementation of recurrent spiking neurons and classical feed forward networks for an application of isolated digit recognition. The structure of this
chapter is as follows: section 2 elaborates the motivation, related work, theoretical review
and description of the paradigm of reservoir computing. Section 3 contains details about the
experimental setup and investigates front-end pre-processing techniques and reservoir
dynamics. A baseline feed forward classifier is described in section 4 and results are
presented. Results based on reservoir recognition are presented in section 5. Section 6
discusses results obtained through Poisson spike encoding. A thorough discussion and
conclusion of the chapter is provided in section 7.