Isolated word recognition with the Liquid State Machine: a case study

Verstraeten, David; Schrauwen, Benjamin; Stroobandt, Dirk; Campenhout, J. Van

doi:10.1016/j.ipl.2005.05.019

Cited by 221 publications

(187 citation statements)

References 13 publications

Supporting

Mentioning

176

Contrasting

Unclassified

Order By: Relevance

“…The three schemes are: rate coding, which encodes information in the frequency of spike occurrence, direct temporal coding, which uses the timing of each and every spike for computation, and synchrony coding, which groups neurons with similar firing times. At this step, it is important to note that there have been previous attempts to use spike trains for speech classification (Hopfield and Brody, 2001;Verstraeten et al, 2005). One of the major differences between the proposed architecture and these approaches is the enforcement of the spike coding schemes on top of the spike trains from the cochlea.…”

Section: Spike Coding Techniques and Their Application To Nerve Fibersmentioning

confidence: 99%

Towards Spike-Based Speech Processing: A Biologically Plausible Approach to Simple Acoustic Classification

Uysal¹,

Sathyendra²,

Harris³

2008

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Shortcomings of automatic speech recognition (ASR) applications are becoming more evident as they are more widely used in real life. The inherent non-stationarity associated with the timing of speech signals as well as the dynamical changes in the environment make the ensuing analysis and recognition extremely difficult. Researchers often turn to biology seeking clues to make better engineered systems, and ASR is no exception with the usage of feature sets such as Mel frequency cepstral coefficients, which employ filter banks similar to cochlear filter banks in frequency distribution and bandwidth. In this paper, we delve deeper into the mechanics of the human auditory system to take this biological inspiration to the next level. The main goal of this research is to investigate the computation potential of spike trains produced at the early stages of the auditory system for a simple acoustic classification task. First, various spike coding schemes from temporal to rate coding are explored, together with various spike-based encoders with various simplicity levels such as rank order coding and liquid state machine. Based on these findings, a biologically plausible system architecture is proposed for the recognition of phonetically simple acoustic signals which makes exclusive use of spikes for computation. The performance tests show superior performance on a noisy vowel data set when compared with a conventional ASR system.

show abstract

Section: Spike Coding Techniques and Their Application To Nerve Fibersmentioning

confidence: 99%

Towards Spike-Based Speech Processing: A Biologically Plausible Approach to Simple Acoustic Classification

Uysal¹,

Sathyendra²,

Harris³

2008

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

“…Considerable work has focused on developing SNNs that are suitable for speech processing [176,58,179,93]. Verstraeten et al [176] develop a model based on Liquid State Machines that is trained to recognize isolated words.…”

Section: Pattern Recognition With Snnsmentioning

confidence: 99%

“…Verstraeten et al [176] develop a model based on Liquid State Machines that is trained to recognize isolated words. They compare several front-end signal encoding methods, and find that a nature-inspired frontend like a "Lyon Passive Ear" outperforms other methods when an LSM is applied.…”

Section: Pattern Recognition With Snnsmentioning

confidence: 99%

Computing with Spiking Neuron Networks

Paugam-Moisy

Bohté

2012

Handbook of Natural Computing

202

114

View full text Add to dashboard Cite

Spiking Neuron Networks (SNNs) are often referred to as the 3 rd generation of neural networks. Highly inspired from natural computing in the brain and recent advances in neurosciences, they derive their strength and interest from an accurate modeling of synaptic interactions between neurons, taking into account the time of spike firing. SNNs overcome the computational power of neural networks made of threshold or sigmoidal units. Based on dynamic event-driven processing, they open up new horizons for developing models with an exponential capacity of memorizing and a strong ability to fast adaptation. Today, the main challenge is to discover efficient learning rules that might take advantage of the specific features of SNNs while keeping the nice properties (general-purpose, easy-to-use, available simulators, etc.) of traditional connectionist models. This chapter relates the history of the "spiking neuron" in Section 1 and summarizes the most currently-in-use models of neurons and synaptic plasticity in Section 2. The computational power of SNNs is addressed in Section 3 and the problem of learning in networks of spiking neurons is tackled in Section 4, with insights into the tracks currently explored for solving it. Finally, Section 5 discusses application domains, implementation issues and proposes several simulation frameworks.

show abstract

“…Different biologically plausible and signal processing based techniques such as frequential based MFCC (Mel Frequency Cepstral Coefficient), Lyon Passive Ear and Inner Hair Cell models have b ee n reported in the literature and a detailed comparison is provided by (Verstraeten et al, 2005). These techniques provide a good analysis but none of them offers an optimal solution.…”

Section: Feature Extractionmentioning

confidence: 99%