Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Automatic speech recognition using a predictive echo state network classifier.

Mark D Skowronski1, John G Harris

  • 1Computational NeuroEngineering Lab, NEB 465, University of Florida, Gainesville, FL 32611, USA. markskow@cnel.ufl.edu

Neural Networks : the Official Journal of the International Neural Network Society
|June 9, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Editorial: Bio-inspired Audio Processing, Models and Systems.

Frontiers in neuroscience·2019
Same author

Perceptual and Quantitative Assessment of Dysphonia Across Vowel Categories.

Journal of voice : official journal of the Voice Foundation·2018
Same author

Comparison of Pitch Strength With Perceptual and Other Acoustic Metric Outcome Measures Following Medialization Laryngoplasty.

Journal of voice : official journal of the Voice Foundation·2018
Same author

The Perception of Breathiness in the Voices of Pediatric Speakers.

Journal of voice : official journal of the Voice Foundation·2017
Same author

Pitch Strength as an Outcome Measure for Treatment of Dysphonia.

Journal of voice : official journal of the Voice Foundation·2017
Same author

Cepstral Peak Sensitivity: A Theoretic Analysis and Comparison of Several Implementations.

Journal of voice : official journal of the Voice Foundation·2015
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

A new predictive echo state network (ESN) classifier offers superior noise robustness for speech recognition tasks compared to traditional hidden Markov models. Its simple training makes it ideal for automatic speech recognition systems.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Signal Processing

Background:

  • Automatic speech recognition (ASR) systems often struggle with noisy environments.
  • Traditional models like Hidden Markov Models (HMMs) have limitations in noise robustness.

Purpose of the Study:

  • To develop a novel classification engine for improved noisy speech classification.
  • To evaluate the noise robustness and training efficiency of the proposed model compared to existing methods.

Main Methods:

  • Integration of an Echo State Network (ESN) with a competitive state machine framework.
  • Derivation of training expressions for the novel predictive ESN classifier.
  • Comparative analysis against a Hidden Markov Model (HMM) in noisy speech classification experiments.

Related Experiment Videos

Main Results:

  • The predictive ESN classifier demonstrated significantly enhanced noise robustness.
  • Achieved an 8+/-1 dB improvement in signal-to-noise ratio (SNR) over HMMs.
  • The model features a simple and efficient training algorithm.

Conclusions:

  • The predictive ESN classifier is a highly noise-robust engine for ASR.
  • Its performance and ease of training make it a promising alternative for ASR applications.
  • Further research can explore its application in diverse noisy acoustic environments.