𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Automatic speech recognition using a predictive echo state network classifier

✍ Scribed by Mark D. Skowronski; John G. Harris


Publisher
Elsevier Science
Year
2007
Tongue
English
Weight
842 KB
Volume
20
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

✦ Synopsis


We have combined an echo state network (ESN) with a competitive state machine framework to create a classification engine called the predictive ESN classifier. We derive the expressions for training the predictive ESN classifier and show that the model was significantly more noise robust compared to a hidden Markov model in noisy speech classification experiments by 8 ± 1 dB signal-to-noise ratio. The simple training algorithm and noise robustness of the predictive ESN classifier make it an attractive classification engine for automatic speech recognition.