Abstract

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. © 2007 Elsevier Ltd. All rights reserved.

Department(s)

Electrical and Computer Engineering

Publication Status

Full Text Access

Keywords and Phrases

Automatic speech recognition; Echo state network; Mixture of experts; Noise robustness

International Standard Serial Number (ISSN)

0893-6080

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Elsevier, All rights reserved.

Publication Date

01 Apr 2007

PubMed ID

17556115

Share

 
COinS