Abstract

Artificial neural networks have been shown to perform well in automatic speech recognition (ASR) tasks, although their complexity and excessive computational costs have limited their use. Recently, a recurrent neural network with simplified training, the echo state network (ESN), was introduced by Jaeger and shown to outperform conventional methods in time series prediction experiments. We created the predictive ESN classifier by combining the ESN with a state machine framework. In small-vocabulary ASR experiments, we compared the noise-robust performance of the predictive ESN classifier with a hidden Markov model (HMM) as a function of model size and signal-to-noise ratio (SNR). The predictive ESN classifier outperformed an HMM by 8-dB SNR, and both models achieved maximum noise-robust accuracy for architectures with more states and fewer kernels per state. Using ten trials of random sets of training/validation/ test speakers, accuracy for the predictive ESN classifier, averaged between 0- and 20-dB SNR, was 81plusmn3%, compared to 61plusmn2% for an HMM. The closed-form regression training for the ESN significantly reduced the computational cost of the network, and the reservoir of the ESN created a high-dimensional representation of the input with memory which led to increased noise-robust classification. © 2007 IEEE.

Department(s)

Electrical and Computer Engineering

Keywords and Phrases

Digit recognition; Noise-robust automatic speech recognition; Predictive echo state network

International Standard Serial Number (ISSN)

1558-7916

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Jan 2007

Download

Full Text Link

Share

 
COinS